INDEX

Explanations

words and phrases describing nursing positions

oai_token-act-pair · gemini-2.0-flash

variations of "part"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

unnitel

-0.53

 Meksiku

-0.49

TintMode

-0.48

нциклопе

-0.47

transQ

-0.46

 resourceCulture

-0.46

 ModelExpression

-0.45

Varint

-0.45

Демографія

-0.45

 invers

-0.44

POSITIVE LOGITS

 part

3.48

part

3.03

Part

2.67

 Part

2.50

 parte

2.13

 PART

2.11

 Teil

1.88

PART

1.82

 часть

1.73

 bagian

1.56

Activations Density 6.929%

words and phrases describing nursing positions

variations of "part"

No Comments

No Known Activations